Change in Quantitative Bipolar Argumentation: Sufficient, Necessary, and Counterfactual Explanations

2025-09-21

AI Summary

This paper addresses the “strength inconsistency” problem in Quantitative Bipolar Argumentation Frameworks (QBAFs)—namely, unintended reversals in the relative strength ordering of arguments under repeated dynamic updates—by proposing a formal explainability framework. We first formally define three classes of explanations—sufficient, necessary, and counterfactual—to characterize the root causes of strength inconsistency and derive precise existence conditions for each, thereby establishing a theoretical foundation for explainability under dynamic updates. Leveraging semantic modeling and heuristic search, we design efficient algorithms for automated identification and computation of such explanations. A prototype tool is implemented and empirically evaluated across diverse update scenarios, demonstrating the method’s effectiveness, completeness, and scalability. Our core contribution is the first systematic causal explanation theory for dynamic inference changes in QBAFs, coupled with a computationally tractable and verifiable attribution mechanism for strength inconsistency.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

This paper presents a formal approach to explaining change of inference in Quantitative Bipolar Argumentation Frameworks (QBAFs). When drawing conclusions from a QBAF and updating the QBAF to then again draw conclusions (and so on), our approach traces changes -- which we call strength inconsistencies -- in the partial order over argument strengths that a semantics establishes on some arguments of interest, called topic arguments. We trace the causes of strength inconsistencies to specific arguments, which then serve as explanations. We identify sufficient, necessary, and counterfactual explanations for strength inconsistencies and show that strength inconsistency explanations exist if and only if an update leads to strength inconsistency. We define a heuristic-based approach to facilitate the search for strength inconsistency explanations, for which we also provide an implementation.

Problem

• Explaining inference changes in Quantitative Bipolar Argumentation Frameworks
• Identifying causes of strength inconsistencies in argument ordering
• Providing sufficient, necessary, and counterfactual explanation types

Innovation

• Formal approach for explaining inference changes
• Identifies sufficient necessary counterfactual explanations
• Heuristic-based search method with implementation